{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30476929", "kind": "science-record", "revision": 7, "content_hash": "sha256:8bdce9637e9c81772f59bd72903b1065497569ea2a790983e64ff69d0992f710", "created_at": "2026-11-01T15:40:39Z", "updated_at": "2026-11-01T21:21:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Nucleolar and Spindle Associated Protein 1 (NUSAP1) Inhibits Cell Proliferation and Enhances Susceptibility to Epirubicin In Invasive Breast Cancer Cells by Regulating Cyclin D Kinase (CDK1) and DLGAP5 Expression.", "doi": "10.12659/MSM.910364", "pmid": "30476929", "authors": ["Xi Zhang", "Yuliang Pan", "Huiqun Fu", "Juan Zhang"], "journal": "Medical science monitor : international medical journal of experimental and clinical research", "year": 2018, "abstract": "BACKGROUND Differentially expressed genes (DEGs) of IBC were selected from the Gene Expression Omnibus (GEO) chip data: GSE21422 and GSE21974. Network analysis of the DEGs and IBC-related genes was performed in STRING database to find the core gene. Thus, this study aimed to determine the role of NUSAP1 in invasive breast cancer (IBC) and to investigate its effect on drug susceptibility to epirubicin (E-ADM). MATERIAL AND METHODS The mRNA expression of NUSAP1 was determined by quantitative polymerase chain reaction (q-PCR). The protein expression was detected by Western blotting. Cell growth and growth cycle were detected by MTT assay and flow cytometry, respectively. Cell migration and invasion were tested by Transwell assay. RESULTS Through use of gene network analysis, we found that NUSAP1 interacts with IBC-related genes. NUSAP1 presented high expression in IBC tissue samples and MCF-7 cells. NUSAP1 overexpression promoted the growth, migration, and invasion of MCF-7 cells. While NUSAP1 gene silencing downregulated the expression of genes associated with cell cycle progression in G2/M phase, cyclin D kinase (CDK1) and DLGAP5 arrested cells in G2/M phase and significantly inhibited the growth, migration, and invasion of MCF-7 cells. si-NUSAP1 increased the susceptibility of MCF-7 cells to E-ADM-induced apoptosis. CONCLUSIONS Our study provides evidence that downregulation of NUSAP1 can inhibit the proliferation, migration, and invasion of IBC cells by regulating CDK1 and DLGAP5 expression and enhances the drug susceptibility to E-ADM.", "claims": [{"id": "claim-method", "statement": "Measurement data are expressed as mean ± standard deviation (SD) and were analyzed by t test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30476929", "locator": "sections[15] \"Statistical analysis\" paragraph 2", "quote": "Measurement data are expressed as mean ± standard deviation (SD) and were analyzed by t test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data set GSE21974 was obtained from the Gene Expression Omnibus (GEO) (http://www.nebi.nlm.nih.gov/geo) with “invasive breast cancer” and/or “neoadjuvant chemotherapy” as the key words. The chip platform was Agilent-014850 Whole Human Genome Microarray 4×44k G4112F (GPL 6480). GSE21974 included 57 samples (32 invasive breast cancer samples before treatment and 25 invasive breast cancer samples after treatment).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30476929", "locator": "sections[3] \"Gene chip data processing\" paragraph 2", "quote": "The data set GSE21974 was obtained from the Gene Expression Omnibus (GEO) (http://www.nebi.nlm.nih.gov/geo) with “invasive breast cancer” and/or “neoadjuvant chemotherapy” as the key words. The chip platform was Agilent-014850 Whole Human Genome Microarray 4×44k G4112F (GPL 6480). GSE21974 included 57 samples (32 invasive breast cancer samples before treatment and 25 invasive breast cancer samples after treatment)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:30476929"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE21422"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE21422"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30476929", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.12659/MSM.910364", "sha256": "sha256:ae522186f69f8e828cedd044f1bbed401c3722b93060b1b4d340ef11f32d68f3", "bytes": 24079, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.12659/MSM.910364", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6278864", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE21422", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE21422", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE21422", "version": null, "note": "The data set GSE21974 was obtained from the Gene Expression Omnibus (GEO) (http://www.nebi.nlm.nih.gov/geo) with “invasive breast cancer” and/or “neoadjuvant chemotherapy” as the key words. The chip platform was Agilent-014850 Whole Human Genome Microarray 4×44k G4112F (GPL 6480). GSE21974 included 57 samples (32 invasive breast cancer samples before treatment and 25 invasive breast cancer samples after treatment).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data set GSE21974 was obtained from the Gene Expression Omnibus (GEO) (http://www.nebi.nlm.nih.gov/geo) with “invasive breast cancer” and/or “neoadjuvant chemotherapy” as the key words. The chip platform was Agilent-014850 Whole Human Genome Microarray 4×44k G4112F (GPL 6480). GSE21974 included 57 samples (32 invasive breast cancer samples before treatment and 25 invasive breast cancer samples after treatment).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM535604", "GSM535605", "GSM535606", "GSM535607", "GSM535608", "GSM535609", "GSM535610", "GSM535611", "GSM535612", "GSM535613", "GSM535614", "GSM535615", "GSM535616", "GSM535617", "GSM535618", "GSM535619", "GSM535620", "GSM535621", "GSM535622"], "sample_count": 19, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression profiling of human DCIS and invasive ductal breast carcinoma", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE21974", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE21974", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE21974", "version": null, "note": "The data set GSE21974 was obtained from the Gene Expression Omnibus (GEO) (http://www.nebi.nlm.nih.gov/geo) with “invasive breast cancer” and/or “neoadjuvant chemotherapy” as the key words. The chip platform was Agilent-014850 Whole Human Genome Microarray 4×44k G4112F (GPL 6480). GSE21974 included 57 samples (32 invasive breast cancer samples before treatment and 25 invasive breast cancer samples after treatment).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data set GSE21974 was obtained from the Gene Expression Omnibus (GEO) (http://www.nebi.nlm.nih.gov/geo) with “invasive breast cancer” and/or “neoadjuvant chemotherapy” as the key words. The chip platform was Agilent-014850 Whole Human Genome Microarray 4×44k G4112F (GPL 6480). GSE21974 included 57 samples (32 invasive breast cancer samples before treatment and 25 invasive breast cancer samples after treatment).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM546381", "GSM546382", "GSM546383", "GSM546384", "GSM546385", "GSM546386", "GSM546387", "GSM546388", "GSM546389", "GSM546390", "GSM546391", "GSM546392", "GSM546393", "GSM546394", "GSM546395", "GSM546396", "GSM546397", "GSM546398", "GSM546399", "GSM546400", "GSM546401", "GSM546402", "GSM546403", "GSM546404", "GSM546405", "GSM546406", "GSM546407", "GSM546408", "GSM546409", "GSM546410", "GSM546411", "GSM546412", "GSM546413", "GSM546414", "GSM546415", "GSM546416", "GSM546417", "GSM546418", "GSM546419", "GSM546420", "GSM546421", "GSM546422", "GSM546423", "GSM546424", "GSM546425", "GSM546426", "GSM546427", "GSM546428", "GSM546429", "GSM546430", "GSM546431", "GSM546432", "GSM546433", "GSM546434", "GSM546435", "GSM546436", "GSM546437"], "sample_count": 57, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Molecular Subtype Predicts Response to Neoadjuvant Chemotherapy in Breast Cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:30476929:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:43dd754dba1bfb40281ff1ea2bb739c9cc3f62c62289dcfd061a4bd01c49a1b5", "bytes": 3103, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[26]/table-wrap[1]#t1-medscimonit-24-8553", "version": null, "note": "List of detailed genes selected by network-based meta-analysis in the study.", "structure": {"pmcid": "PMC6278864", "section_index": 26, "section_title": "Supplementary Tables", "row_count": 57, "column_count": 6}, "table": {"label": "Supplementary Table 1.", "caption": "List of detailed genes selected by network-based meta-analysis in the study.", "rows": [["Name", "Name", "Name", "Name", "Name", "Name"], ["IGF1", "IGFBP4", "OLFML3", "ZBTB16", "COPZ2", "KERA"], ["C19orf80", "SLC2A4", "ATP1B2", "FAM72D", "ENPP2", "C2orf40"], ["VWF", "OAF", "MRAP", "CDK1", "FOXM1", "TNIP3"], ["COL14A1", "FBLN1", "EXO1", "PTTG2", "DGAT2", "HJURP"], ["NCAPH", "MMP23B", "OIP5", "CCL20", "KIF4A", "C3"], ["PPAP2A", "LPL", "PLIN1", "IL33", "KL", "RRAD"], ["SDPR", "KIF11", "HAPLN1", "PLK1", "EPHX1", "DMRT2"], ["CD36", "AKAP12", "RAD51", "PBK", "CXCL14", "ATOH8"], ["FXYD1", "SCRN2", "AOC3", "SPAG5", "PDGFRL", "TUSC5"], ["GDF10", "LAMA2", "C15orf42", "MME", "KCNB1", "CLDN19"], ["RAD54L", "SFRP4", "C1QTNF7", "MMRN1", "RDH5", "AQP7P2"], ["UHRF1", "MCM10", "CMA1", "ABLIM3", "MAOA", "GSTM2"], ["TNNT3", "DARC", "F10", "PCOLCE", "CA4", "TPX2"], ["KIF23", "PRC1", "ESCO2", "HIST1H1B", "G0S2", "CCNA2"], ["FAM64A", "CD300LG", "CES1", "TSHZ2", "ELTD1", "TSC22D3"], ["TGFBR3", "ALDH1A1", "TFPI", "SAMD5", "CA3", "NUSAP1"], ["PDE2A", "LEP", "PTTG1", "C16orf89", "MMP11", "TMEM100"], ["ITIH5", "JAM2", "C1QTNF9B", "LUZP2", "TIMP4", "FAM83D"], ["FHL1", "MEOX2", "CENPA", "ACACB", "APOD", "SERPING1"], ["AKR1C3", "ROBO4", "PHYHIP", "CAV2", "ELN", "EMX2"], ["CEP55", "LDB2", "GSC", "PODN", "PTN", "FLNC"], ["TROAP", "THRSP", "RPSA", "NNAT", "CAMK1", "PDLIM1"], ["DLGAP5", "C16orf59", "RERGL", "MMP1", "FREM1", "PCK1"], ["HRC", "CDCA8", "ZWINT", "CFD", "PAMR1", "CYP4F22"], ["CDCA5", "BLM", "RBP4", "CENPE", "AKR1C1", "FIGF"], ["IGFBP6", "PPARG", "CKS2", "OMD", "HOXA5", "1-Mar"], ["TK1", "CD34", "SEMA3G", "CKMT2", "ERCC6L", "DEPDC1B"], ["TSPAN7", "VWCE", "DEPDC1", "ANGPTL1", "HABP4", "CCDC8"], ["ASPM", "RDM1", "CYGB", "PID1", "ZNF695", "ART5"], ["GPC3", "DPT", "CPZ", "AGPAT2", "ITGA7", "NMU"], ["E2F1", "FAM54A", "OGN", "HSPB7", "PPP1R1A", "LHX2"], ["POLQ", "MATN2", "SCN2B", "NPR1", "FABP4", "MYOM2"], ["CLDN5", "PLIN4", "ASPA", "NDN", "ACADS", "SOX11"], ["HMMR", "FANCA", "ABCA8", "LOC100128164", "RARRES2", "CFHR4"], ["KIF2C", "NGFR", "SLIT2", "KIFC1", "MYZAP", "TREM1"], ["CDKN1C", "MAB21L1", "PTH1R", "PDGFD", "GIMAP7", "TTK"], ["EMCN", "CIDEC", "MFAP4", "LRRC17", "MMP2", "LGALS12"], ["EZH2", "NEK2", "BMX", "MYOC", "GAS6", "PDZRN3"], ["IL11RA", "OSR1", "H19", "MEOX1", "MELK", "ANGPTL7"], ["HSPA12B", "C7", "MAMDC2", "CDH5", "MYH11", "MYRIP"], ["FLRT2", "RNASE4", "RHOJ", "CENPF", "DAAM2", "CITED1"], ["BTNL9", "TNMD", "C4orf49", "C1orf115", "BOC", "CDKN3"], ["SGOL1", "SKA3", "VIPR2", "C5orf46", "CMTM5", "TCEA2"], ["CLEC14A", "EBF1", "CLEC3B", "EBF3", "DENND2A", "HLF"], ["CCDC80", "CDO1", "CIDECP", "GPX3", "TPO", "BCHE"], ["DTL", "ABCA9", "DIO3OS", "OLR1", "CRTAC1", "MIR143HG"], ["SLC25A18", "ITM2A", "E2F8", "CDC25C", "EDN3", "ANLN"], ["BIRC5", "SHE", "RAMP3", "MYBL2", "TPSAB1", "MMP12"], ["ADIPOQ", "IL1B", "E2F7", "C18orf34", "HAMP", "PEBP4"], ["GPD1", "GUCA2B", "SPC25", "GPIHBP1", "LOC572558", "LYVE1"], ["CAV1", "PYGM", "GSTM5", "PCDH12", "LOC100507537", "ANKRD29"], ["NCAPG", "ADH1A", "ABCB1", "KIF18A", "IGF2", "4-Sep"], ["GPAM", "ZCCHC24", "SRPX", "CDCA2", "RSPO3", "GTSE1"], ["UBE2C", "ADH1C", "AVPR2", "CKAP2L", "FGF2", "PLP1"], ["SCN4B", "PKMYT1", "SELP", "CPXM1", "TF", "KIF20A"], ["CDC45", "UBE2T", "DNASE1L3", "CDCA3", "SFRP2", "BUB1"]], "row_count": 57, "column_count": 6, "numeric_cells": 63, "header_rows": 1, "locator": "section[26]/table-wrap[1]#t1-medscimonit-24-8553"}}, {"id": "asset:table:pmid:30476929:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cedecef183b18697f26b8aafad433f9cdd516e74cb8d8cb463efea717701d598", "bytes": 377, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[26]/table-wrap[2]#t2-medscimonit-24-8553", "version": null, "note": "IBC-related genes were downloaded from the../../../../Documents/tencent files/1002826528/filerecv/the database.", "structure": {"pmcid": "PMC6278864", "section_index": 26, "section_title": "Supplementary Tables", "row_count": 5, "column_count": 2}, "table": {"label": "Supplementary Table 2.", "caption": "IBC-related genes were downloaded from the../../../../Documents/tencent files/1002826528/filerecv/the database.", "rows": [["Name", "Name"], ["ERBB2", "CD324"], ["EGFR", "GFRP1"], ["ESR1", "PPIG"], ["NR3C3", "RAD1"]], "row_count": 5, "column_count": 2, "numeric_cells": 1, "header_rows": 1, "locator": "section[26]/table-wrap[2]#t2-medscimonit-24-8553"}}], "gaps": ["asset:data:geo:GSE21422 not downloaded", "asset:data:geo:GSE21422 licence not read", "asset:data:geo:GSE21974 not downloaded", "asset:data:geo:GSE21974 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "t test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Measurement data are expressed as mean ± standard deviation (SD) and were analyzed by t test."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (t test), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE21974", "GSE21422"], "resolved_accessions": ["GSE21974", "GSE21422"], "statements": ["The data set GSE21974 was obtained from the Gene Expression Omnibus (GEO) (http://www.nebi.nlm.nih.gov/geo) with “invasive breast cancer” and/or “neoadjuvant chemotherapy” as the key words. The chip platform was Agilent-014850 Whole Human Genome Microarray 4×44k G4112F (GPL 6480). GSE21974 included 57 samples (32 invasive breast cancer samples before treatment and 25 invasive breast cancer samples after treatment)."], "basis": "The paper names GSE21974, GSE21422 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:30476929", "data:geo:GSE21422", "asset:table:pmid:30476929:1", "asset:table:pmid:30476929:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE21422"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:12:56Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 21453, "completion_tokens": 1617, "cached_tokens": 784}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:30476929", "type": "paper", "label": "pmid:30476929"}, {"id": "source:pmid:30476929", "type": "manuscript", "label": "PMID 30476929 full text"}, {"id": "data:geo:GSE21422", "type": "dataset", "label": "GEO GSE21422"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30476929", "type": "paper", "label": "pmid:30476929"}, {"id": "source:pmid:30476929", "type": "manuscript", "label": "PMID 30476929 full text"}, {"id": "data:geo:GSE21422", "type": "dataset", "label": "GEO GSE21422"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30476929", "type": "extraction", "used": ["source:pmid:30476929"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE21422", "type": "accession_resolution", "used": ["data:geo:GSE21422"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:30476929", "parent_hash": "sha256:2f98e079cfcd219a3ec058caf5d40f1cbc4a1041cf436f15fe661225433b8822", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE21422 licence not read", "asset:data:geo:GSE21422 not downloaded", "asset:data:geo:GSE21974 licence not read", "asset:data:geo:GSE21974 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["PCR). The protein expression was detected by Western blotting. Cell growth and growth cycle were detected"], "order_basis": "paper_text_order:738", "id": "assay:1"}, {"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["sceptibility of MCF-7 cells to E-ADM-induced apoptosis. CONCLUSIONS Our study provides evidence tha", "ell growth and growth cycle were detected by MTT assay and flow cytometry, respectively. Cell"], "order_basis": "paper_text_order:802", "id": "assay:2"}, {"role": "data_generation", "definition_id": "flow_cytometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["growth cycle were detected by MTT assay and flow cytometry, respectively. Cell migration and invasion w"], "order_basis": "paper_text_order:817", "id": "assay:3"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ed high expression in IBC tissue samples and MCF-7 cells. NUSAP1 overexpression promoted the gr", "moted the growth, migration, and invasion of MCF-7 cells. While NUSAP1 gene silencing downregul", "bited the growth, migration, and invasion of MCF-7 cells. si-NUSAP1 increased the susceptibilit", "s. si-NUSAP1 increased the susceptibility of MCF-7 cells to E-ADM-induced apoptosis. CONCLUSION"], "order_basis": "paper_text_order:1066", "id": "assay:4"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["atform was Agilent-014850 Whole Human Genome Microarray 4×44k G4112F (GPL 6480). GSE21974 included 5"], "order_basis": "paper_text_order:2026", "id": "assay:5"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:36:47+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}